Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/st0012/cctop/e2e-session-testnpx skills add st0012/cctop --skill e2e-session-testgit clone --depth 1 https://github.com/st0012/cctopWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/st0012/cctop/e2e-session-test)<a href="https://agentmods.dev/skills/st0012/cctop/e2e-session-test"><img src="https://agentmods.dev/badge/skills/st0012/cctop/e2e-session-test.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00112 | $0.00753 |
| Opus 5 | $0.00056 | $0.00377 |
| Sonnet 5 | $0.00022 | $0.00151 |
| Haiku 4.5 | $0.00011 | $0.00075 |
Grade A, and why
e2e-session-test scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
cctop end-to-end session test
Verify a real session flows all the way through:
agent in a terminal → cctop hooks → ~/.cctop/sessions/<pid>.json → panel card
A good smoke test after touching hooks, the session schema, or the panel.
Capabilities, not tools
Harness-agnostic — it needs three generic capabilities. Use your environment's equivalent; don't assume a specific tool:
- run shell commands
- capture a screenshot of the screen (or fall back to the
screencaptureCLI) - view an image you captured
Create the session with a CLI agent in a terminal
Drive a CLI agent (claude / codex / opencode / pi) in a terminal window —
it's a real session and one shell command starts it. Don't try to puppet a
desktop agent's GUI: if it's the app hosting you, screen capture hides its window
and you can't confirm input landed (see references/troubleshooting.md). Requires a
cctop build with the cctop:// URL scheme (ships with this skill).
Steps (run from the repo root)
# 1. Baseline — note the PIDs
.claude/skills/e2e-session-test/scripts/cctop-sessions.sh
# 2. Create a session — opens a terminal running the agent, waits for it to register
.claude/skills/e2e-session-test/scripts/launch-cli-session.sh claude ~/projects/cctop
# 3. Verify — a new PID entry with the right source (cc/codex/opencode/pi) appears
.claude/skills/e2e-session-test/scripts/cctop-sessions.sh
# 4. Summon the panel
open cctop://toggle
Then capture a screenshot and confirm the new session's card is in the panel
(right status, source, project). Run open cctop://toggle again to close it — a
clean closed/open pair if you want before/after proof. For a shareable record,
write a small HTML log embedding the screenshots.
Two details the launcher handles, because they otherwise make this fail silently: a
login shell (so the agent's PATH, e.g. ~/.local/bin, resolves) and a
trusted directory (so the agent doesn't stall at a folder-trust prompt).
open cctop://toggle is used instead of a menu-bar click or hotkey because those
need extra OS permissions under automation.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 74 lines · 112 tokens per session scan A f1fb73829200
e2e-session-test is a skill published in the GitHub repository st0012/cctop (148 stars, last pushed 3d ago), licensed MIT. It adds 112 tokens to every session and 753 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
moai-domain-html-report
Markdown-to-single-file-HTML report renderer. Six modes (status, incident, plan, explainer, financial, pr) selected by report type, crossed with three audience tiers (expert, basic, learn) derived from the active output style. The basic and learn tiers enrich the HTML with mermaid flowcharts, worked examples, and…
task-implement
Automated batch implementation: auto-implements ALL incomplete tasks from a task document without user interaction, then runs automated code review. Only use when the user explicitly requests automated/batch task implementation.
generate-plan
Generate a comprehensive plan document (计划书/計劃書) from requirements, backlog items, or specs. Adapts to project-specific templates. Includes collaborative discussion, self-challenge, and automated verification via review agent. Three phases: Discover, Plan, Verify. Trigger on: "write a plan", "generate plan", "写计划书"…
generate-brief
Structured discovery conversation that produces a requirement brief (需求摘要). Use when the idea is too vague to plan directly, when you need to think through an idea before committing, or when you need a shareable document before planning. Not for creating plans — use generate-plan instead. Trigger on: "help me think…
generate-task
Generate a fine-grained task document (任务文档/任务分解) from a plan document. Reads actual code to determine correct decomposition, then self-reviews via review agent. Trigger on: "generate tasks", "break down tasks", "create task document", "拆任务", "生成任务", "任务分解", "帮我拆任务".
moai-docs-generation
Documentation generation patterns for technical specs, API docs, user guides, and knowledge bases using real tools like Sphinx, MkDocs, TypeDoc, and Nextra. Use when creating docs from code, building doc sites, or automating documentation workflows.